Detectree2

Detectree2, based on the Detectron2 Mask R-CNN architecture, locates trees in aerial images. It has been designed to delineate trees in challenging dense tropical forests for a range of ecological applications. Below is an example image of the predictions made by Detectree2.

Code developed by James Ball, Seb Hickman, Thomas Koay, Oscar Jiang, Luran Wang, Panagiotis Ioannou, James Hinton and Matthew Archer in the Forest Ecology and Conservation Group at the University of Cambridge. The Forest Ecology and Conservation Group is led by Professor David Coomes and is part of the University of Cambridge Conservation Research Institute. MRes project repo available here.

Citation

Ball, J.G.C., Hickman, S.H.M., Jackson, T.D., Koay, X.J., Hirst, J., Jay, W., Archer, M., Aubry-Kientz, M., Vincent, G. and Coomes, D.A. (2023) Accurate delineation of individual tree crowns in tropical forests from aerial RGB imagery using Mask R-CNN. Remote Sens Ecol Conserv. https://doi.org/10.1002/rse2.332

Contents:

• 1. Installation
  • 1.1. Building Detectree2
• 2. Tutorial
  • 2.1. Preparing data (RGB/multispectral)
  • 2.2. Training (RGB)
  • 2.3. Training (multispectral)
  • 2.4. Data augmentation
  • 2.5. Post-training (check convergence)
  • 2.6. Performance metrics
  • 2.7. Evaluating model performance
  • 2.8. Generating landscape predictions
• 3. Tutorial (multiclass)
  • 3.1. Preparing data
  • 3.2. Training models
  • 3.3. Landscape predictions
• 4. Contributing guide
  • 4.1. Contributing to Detectree2
  • 4.2. Detectree2 setup for developers
  • 4.3. Continuous integration
  • 4.4. Automatic Documentation
  • 4.5. Tests
  • 4.6. Building Detectree2
  • 4.7. Python development environment
• 5. Git/Github
  • 5.1. Overview
  • 5.2. More advanced Git Practices

Indices and tables

• Index

• Module Index

• Search Page